© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50217
    Prev
    Next
    INDEX
    Explanations

    character art and animation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects items in enumerations or list-like sequences, especially commas and the surrounding list entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     버튼
    -0.82
    Kras
    -0.77
    Prizes
    -0.76
     dete
    -0.75
     vagina
    -0.71
    rimid
    -0.71
    hton
    -0.69
    pug
    -0.68
    Segue
    -0.68
    INDIC
    -0.67
    POSITIVE LOGITS
     art
    2.64
     artwork
    2.25
     Art
    1.82
    Art
    1.80
     artworks
    1.71
    art
    1.64
     official
    1.53
     Artwork
    1.44
    artwork
    1.43
     arts
    1.33
    Activations Density 0.037%

    No Known Activations